In this paper we propose an audio feature for TwinVQ audio retrieval. For making effective audio database, we consider that on one platform these two techniques (compression arid feature extraction) are dealt with. The proposed audio feature satisfies the following requirements: 1) independence of bit rate 2) extractable from compressed data 3) computable in the framework of TwinVQ. We show that the autocorrelation coefficient is theoretically independent of bit rate and confirm experimentally that the computed feature from CD audio data is actually independent of bit rate.
展开▼